ipv6: fix incorrect ipsec fragment

[ Upstream commit 0c1833797a5a6ec23ea9261d979aa18078720b74 ]

Since commit ad0081e43a
"ipv6: Fragment locally generated tunnel-mode IPSec6 packets as needed"
the fragment of packets is incorrect.
because tunnel mode needs IPsec headers and trailer for all fragments,
while on transport mode it is sufficient to add the headers to the
first fragment and the trailer to the last.

so modify mtu and maxfraglen base on ipsec mode and if fragment is first
or last.

with my test,it work well(every fragment's size is the mtu)
and does not trigger slow fragment path.

Changes from v1:
	though optimization, mtu_prev and maxfraglen_prev can be delete.
	replace xfrm mode codes with dst_entry's new frag DST_XFRM_TUNNEL.
	add fuction ip6_append_data_mtu to make codes clearer.

Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 54 insertions, 18 deletions

diff --git a/include/net/dst.h b/include/net/dst.h
index d0201340bee2..7907ff15e0fd 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -78,6 +78,7 @@ struct dst_entry {
 #define DST_NOHASH		0x0008
 #define DST_NOCACHE		0x0010
 #define DST_NOCOUNT		0x0020
+#define DST_XFRM_TUNNEL		0x0100
 	union {
 		struct dst_entry	*next;
 		struct rtable __rcu	*rt_next;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 9cbf17686a1b..ae9f6d436171 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1194,6 +1194,29 @@ static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src,
 	return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
 }
 
+static void ip6_append_data_mtu(int *mtu,
+				int *maxfraglen,
+				unsigned int fragheaderlen,
+				struct sk_buff *skb,
+				struct rt6_info *rt)
+{
+	if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
+		if (skb == NULL) {
+			/* first fragment, reserve header_len */
+			*mtu = *mtu - rt->dst.header_len;
+
+		} else {
+			/*
+			 * this fragment is not first, the headers
+			 * space is regarded as data space.
+			 */
+			*mtu = dst_mtu(rt->dst.path);
+		}
+		*maxfraglen = ((*mtu - fragheaderlen) & ~7)
+			      + fragheaderlen - sizeof(struct frag_hdr);
+	}
+}
+
 int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	int offset, int len, int odd, struct sk_buff *skb),
 	void *from, int length, int transhdrlen,
@@ -1203,7 +1226,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct inet_cork *cork;
-	struct sk_buff *skb;
+	struct sk_buff *skb, *skb_prev = NULL;
 	unsigned int maxfraglen, fragheaderlen;
 	int exthdrlen;
 	int hh_len;
@@ -1260,8 +1283,12 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		inet->cork.fl.u.ip6 = *fl6;
 		np->cork.hop_limit = hlimit;
 		np->cork.tclass = tclass;
-		mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
-		      rt->dst.dev->mtu : dst_mtu(rt->dst.path);
+		if (rt->dst.flags & DST_XFRM_TUNNEL)
+			mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+			      rt->dst.dev->mtu : dst_mtu(&rt->dst);
+		else
+			mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+			      rt->dst.dev->mtu : dst_mtu(rt->dst.path);
 		if (np->frag_size < mtu) {
 			if (np->frag_size)
 				mtu = np->frag_size;
@@ -1356,38 +1383,43 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 			unsigned int fraglen;
 			unsigned int fraggap;
 			unsigned int alloclen;
-			struct sk_buff *skb_prev;
 alloc_new_skb:
-			skb_prev = skb;
-
 			/* There's no room in the current skb */
-			if (skb_prev)
-				fraggap = skb_prev->len - maxfraglen;
+			if (skb)
+				fraggap = skb->len - maxfraglen;
 			else
 				fraggap = 0;
+			/* update mtu and maxfraglen if necessary */
+			if (skb == NULL || skb_prev == NULL)
+				ip6_append_data_mtu(&mtu, &maxfraglen,
+						    fragheaderlen, skb, rt);
+
+			skb_prev = skb;
 
 			/*
 			 * If remaining data exceeds the mtu,
 			 * we know we need more fragment(s).
 			 */
 			datalen = length + fraggap;
-			if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
-				datalen = maxfraglen - fragheaderlen;
 
-			fraglen = datalen + fragheaderlen;
+			if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
+				datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
 			if ((flags & MSG_MORE) &&
 			    !(rt->dst.dev->features&NETIF_F_SG))
 				alloclen = mtu;
 			else
 				alloclen = datalen + fragheaderlen;
 
-			/*
-			 * The last fragment gets additional space at tail.
-			 * Note: we overallocate on fragments with MSG_MODE
-			 * because we have no idea if we're the last one.
-			 */
-			if (datalen == length + fraggap)
-				alloclen += rt->dst.trailer_len;
+			if (datalen != length + fraggap) {
+				/*
+				 * this is not the last fragment, the trailer
+				 * space is regarded as data space.
+				 */
+				datalen += rt->dst.trailer_len;
+			}
+
+			alloclen += rt->dst.trailer_len;
+			fraglen = datalen + fragheaderlen;
 
 			/*
 			 * We just reserve space for fragment header.
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 7803eb6af414..0c0e40e9cfc1 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1917,6 +1917,9 @@ no_transform:
 	}
 ok:
 	xfrm_pols_put(pols, drop_pols);
+	if (dst && dst->xfrm &&
+	    dst->xfrm->props.mode == XFRM_MODE_TUNNEL)
+		dst->flags |= DST_XFRM_TUNNEL;
 	return dst;
 
 nopol: